paperAugust 2026Unreviewed

MalTotal: Cost-Effective and Language-Agnostic Malicious Code Poisoning Detection for Millions of Repositories

Jian Zhao, Shenao Wang, Qingyang Wu, Yanjie Zhao, Xiao Cheng, Hao-Yu Wang

Abstract

The widespread adoption of open source software (OSS) has introduced significant security risks, with malicious code poisoning attacks increasingly targeting public package registries and open-source platforms. Existing detection approaches, including heuristic-, learning-, and LLM-based methods, suffer from language-specific designs, limited generalization, and high analysis costs, making them unsuitable for large-scale multi-language analysis. To address these challenges, we propose MalTotal,

Framework mappings

OWASP Top 10 for LLM Applications

LLM04Data and Model Poisoning

MITRE ATLAS

AML.T0020Poison Training Data

Suggested from the entry's categories.

Cite

@misc{zhao2026maltotal,
  title = {{MalTotal: Cost-Effective and Language-Agnostic Malicious Code Poisoning Detection for Millions of Repositories}},
  author = {Jian Zhao and Shenao Wang and Qingyang Wu and Yanjie Zhao and Xiao Cheng and Hao-Yu Wang},
  year = {2026},
  month = aug,
  eprint = {2608.03232},
  archivePrefix = {arXiv},
  doi = {10.1145/3832228},
  url = {https://www.semanticscholar.org/paper/4ab91ee574adb3a457dd6e506a4cd327af5a1fd1}
}